Skip to content

Can elektronn3 load models trained on elektronn2? #48

Answered by mdraw
jmlipman asked this question in Q&A
Discussion options

You must be logged in to vote

Hi, this is not straightforward because elektronn2 is based on Theano and elektronn3 is based on PyTorch. Theoretically you can export elektronn2 network weights to an equivalent PyTorch-based network by copying them by hand with NumPy but I would recommend just retraining from scratch with elektronn3 instead.

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by mdraw
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants